Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 438
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to light and its properties

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to light and its interactions with gravity and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itaire
    -0.78
    utch
    -0.76
    ador
    -0.76
     drawer
    -0.74
    ismo
    -0.73
     furniture
    -0.72
     benches
    -0.72
    ilitarian
    -0.71
    uxe
    -0.70
     Tycoon
    -0.69
    POSITIVE LOGITS
     wavelengths
    1.66
     photons
    1.63
     emitted
    1.59
     wavelength
    1.42
     rays
    1.41
     ultraviolet
    1.38
     radiation
    1.35
    velength
    1.34
     pulses
    1.30
     electromagnetic
    1.29
    Activations Density 0.217%

    No Known Activations